© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54077
    Prev
    Next
    INDEX
    Explanations

    scientific terms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    飫
    -0.10
    CTS
    -0.09
    çıį
    -0.09
    axed
    -0.08
    bur
    -0.08
     sed
    -0.08
    ingo
    -0.08
    imoto
    -0.08
    onation
    -0.08
    oha
    -0.08
    POSITIVE LOGITS
    å¯ĦãģĽ
    0.11
    对æĬĹ
    0.11
    æĬĹè¡¡
    0.11
     ÑģовеÑĢ
    0.10
    ä»£æĽ¿
    0.10
     hã
    0.10
    è¿ľæ´ĭ
    0.09
    éĤ£æł·çļĦ
    0.09
    £¼
    0.09
    è®Ń
    0.09
    Activations Density 0.064%

    No Known Activations